{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T08:25:08Z","timestamp":1787300708864,"version":"build-2736575974"},"reference-count":37,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Ultrason Imaging"],"abstract":"<jats:p>Breast ultrasound (BUS) images are commonly degraded by speckle noise, intensity inhomogeneity, acoustic shadowing, and low contrast, while breast tumors often exhibit irregular morphology, heterogeneous echogenicity, and blurred boundaries. These factors make accurate lesion segmentation difficult. We propose SFENet, an end-to-end spatial-frequency dual-branch image quality enhancement network for BUS tumor segmentation. Built on a U-shaped segmentation framework, SFENet jointly models lesion morphology, global spectral responses, and local image-quality degradation through a wavelet-frequency deformable spatial (WFDS) block. Specifically, the lesion-adaptive deformable scanning (LADS) module captures irregular lesion morphology and long-range spatial dependencies; the unified spectral filtering attention (USFA) module performs learnable Fourier-domain spectral recalibration; and the wavelet image enhancement module (WIEM) conducts local brightness correction and edge-aware contrast enhancement through wavelet sub-band decomposition. Because the enhancement pathway is optimized under segmentation supervision, it tends to strengthen lesion-relevant structural cues rather than generic visual quality alone. Experiments on the public BUSI data set show that SFENet achieves a Dice coefficient of 81.3% and a Jaccard index of 73.5%, outperforming the representative CNN-, Transformer-, and Mamba-based segmentation models included in this study. Qualitative results and Grad-CAM visualizations further suggest that SFENet produces more stable lesion contours in low-contrast, heterogeneous, and boundary-ambiguous cases. These results indicate that joint spatial-frequency modeling with task-driven wavelet-domain enhancement is an effective strategy for automatic BUS tumor segmentation.<\/jats:p>","DOI":"10.1177\/01617346261467356","type":"journal-article","created":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T09:23:47Z","timestamp":1787045027000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["SFENet: A Spatial\u2013Frequency Dual-Branch Image Quality Enhancement Network for Breast Ultrasound Tumor Segmentation"],"prefix":"10.1177","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8551-9849","authenticated-orcid":false,"given":"Mengxiang","family":"Sun","sequence":"first","affiliation":[{"name":"College of Communication and Art Design, USST, University of Shanghai for Science and Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohong","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Communication and Art Design, USST, University of Shanghai for Science and Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengwei","family":"Shen","sequence":"additional","affiliation":[{"name":"College of Communication and Art Design, USST, University of Shanghai for Science and Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,8,18]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2018.11.020"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13534-023-00330-7"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.semcancer.2020.04.002"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-94431-1"},{"key":"e_1_3_2_6_2","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger O","year":"2015","unstructured":"Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. arXiv:1505.04597, 2015.","journal-title":"arXiv:1505.04597"},{"key":"e_1_3_2_7_2","article-title":"An introduction to convolutional neural networks","author":"O\u2019Shea K","year":"2015","unstructured":"O\u2019Shea K, Nash R. An introduction to convolutional neural networks. arXiv:1511.08458, 2015.","journal-title":"arXiv:1511.08458"},{"key":"e_1_3_2_8_2","article-title":"Attention is all you need","author":"Vaswani A","year":"2023","unstructured":"Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. arXiv:1706.03762, 2023.","journal-title":"arXiv:1706.03762"},{"key":"e_1_3_2_9_2","article-title":"An image is worth 16\u00d716 words: transformers for image recognition at scale","volume":"11929","author":"Dosovitskiy A","year":"2021","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16\u00d716 words: transformers for image recognition at scale. arXiv:2010. 11929, 2021.","journal-title":"arXiv:2010"},{"key":"e_1_3_2_10_2","unstructured":"Chen J Lu Y Yu Q et al. TransUNet: transformers make strong encoders for medical image segmentation. arXiv:2102. 04306 2021."},{"key":"e_1_3_2_11_2","article-title":"Mamba: linear-time sequence modeling with selective state spaces","author":"Gu A","year":"2024","unstructured":"Gu A, Dao T. Mamba: linear-time sequence modeling with selective state spaces. arXiv:2312.00752, 2024.","journal-title":"arXiv:2312.00752"},{"key":"e_1_3_2_12_2","article-title":"GlobalMamba: global image serialization for vision Mamba","author":"Wang C","year":"2024","unstructured":"Wang C, Zheng W, Zhou J, Lu J. GlobalMamba: global image serialization for vision Mamba. arXiv:2410.10316, 2024.","journal-title":"arXiv:2410.10316"},{"key":"e_1_3_2_13_2","article-title":"DefMamba: deformable visual state space model","volume":"05794","author":"Liu L","year":"2025","unstructured":"Liu L, Zhang M, Yin J, et al. DefMamba: deformable visual state space model. arXiv:2504. 05794, 2025.","journal-title":"arXiv:2504"},{"key":"e_1_3_2_14_2","article-title":"Is denoising necessary for ultrasound image segmentation deep learning: review and benchmark","author":"Liu F","year":"2023","unstructured":"Liu F, Dong Z, Qin P, et al. Is denoising necessary for ultrasound image segmentation deep learning: review and benchmark. TechRxiv, 2023.","journal-title":"TechRxiv"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2018.04.008"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare10040729"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.107086"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109728"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.101989"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123265"},{"key":"e_1_3_2_21_2","article-title":"Visual Mamba: a survey and new outlooks","author":"Xu R","year":"2024","unstructured":"Xu R, Yang S, Wang Y, Cai Y, Du B, Chen H. Visual Mamba: a survey and new outlooks. arXiv:2404.18861, 2024.","journal-title":"arXiv:2404.18861"},{"key":"e_1_3_2_22_2","article-title":"U-Mamba: enhancing long-range dependency for biomedical image segmentation","author":"Ma J","year":"2024","unstructured":"Ma J, Li F, Wang B. U-Mamba: enhancing long-range dependency for biomedical image segmentation. arXiv:2401.04722, 2024.","journal-title":"arXiv:2401.04722"},{"key":"e_1_3_2_23_2","article-title":"VM-UNet: vision Mamba UNet for medical image segmentation","author":"Ruan J","year":"2024","unstructured":"Ruan J, Li J, Xiang S. VM-UNet: vision Mamba UNet for medical image segmentation. arXiv:2402.02491, 2024.","journal-title":"arXiv:2402.02491"},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Liu J Yang H Zhou HY et al. Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining. arXiv:2402.03302 2024.","DOI":"10.1007\/978-3-031-72114-4_59"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2015.12.006"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-21799-5"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-023-01119-y"},{"key":"e_1_3_2_28_2","article-title":"Learning multi-axis representation in frequency domain for medical image segmentation","author":"Ruan J","year":"2024","unstructured":"Ruan J, Gao J, Xie M, Xiang S. Learning multi-axis representation in frequency domain for medical image segmentation. arXiv:2312.17030, 2024.","journal-title":"arXiv:2312.17030"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e35698"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2020.06.015"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs16193594"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-86315-1"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2019.104863"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3226268"},{"key":"e_1_3_2_35_2","article-title":"Recent advances in medical imaging segmentation: a survey","author":"Bougourzi F","year":"2025","unstructured":"Bougourzi F, Hadid A. Recent advances in medical imaging segmentation: a survey. arXiv:2505.09274, 2025.","journal-title":"arXiv:2505.09274"},{"key":"e_1_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Isensee F Petersen J Klein A et al. nnU-Net: self-adapting framework for U-Net-based medical image segmentation. arXiv:1809.10486 2018.","DOI":"10.1007\/978-3-658-25326-4_7"},{"key":"e_1_3_2_37_2","unstructured":"Cao H Wang Y Chen J et al. Swin-Unet: Unet-like pure transformer for medical image segmentation. arXiv:2105.05537 2021."},{"key":"e_1_3_2_38_2","unstructured":"Li C Liu X Li W et al. U-KAN makes strong backbone for medical image segmentation and generation. arXiv:2406.02918 2024."}],"container-title":["Ultrasonic Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/01617346261467356","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/01617346261467356","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/01617346261467356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T07:57:37Z","timestamp":1787299057000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/01617346261467356"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,18]]},"references-count":37,"alternative-id":["10.1177\/01617346261467356"],"URL":"https:\/\/doi.org\/10.1177\/01617346261467356","relation":{},"ISSN":["0161-7346","1096-0910"],"issn-type":[{"value":"0161-7346","type":"print"},{"value":"1096-0910","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,18]]},"article-number":"01617346261467356"}}